A novel intelligent faults diagnosis approach based on Ada-REIELM and its application to complex chemical processes
Yuan Xu, Xue Jiang, Ming‐Qing Zhang, Yan‐Lin He, Fang Duan · 2018
In this paper, a novel fault diagnosis method integrating a recurrent error incremental extreme learning machine (REIELM) with Adaptive Boosting (AdaBoost) is proposed. EIELM can adaptively select the number of neurons by adding them one by one. For further improving the performance of EIELM, a feedback layer is added between the output layer and the hidden layer for remembering the outputs of hidden layer, and the trend change rate is computed to dynamically update the feedback layer outputs. In addition, as the features of input data have impact on the diagnosis results, AdaBoost algorithm is used to adjust the weights of the output in the training process of REIELM, so that the optimal parameters are obtained. To verify the performance of the proposed method, standard UCI data sets and TE simulation process are selected. Simulation results show that the proposed method achieves better performances in fault diagnosis than traditional approaches.